Conţinutul numărului revistei |
Articolul precedent |
Articolul urmator |
498 9 |
Ultima descărcare din IBN: 2024-01-20 17:27 |
SM ISO690:2012 SCHEGOLEV, Andrey, KLENOV, Nikolai V., BAKURSKIY, Sergey V., SOLOVIEV, Igor I., KUPRIYANOV, Mihail, TERESHONOK , Maxim, SIDORENKO, Anatolie. Tunable superconducting neurons for networks based on radial basis functions. In: Beilstein Journal of Nanotechnology, 2022, vol. 13, pp. 444-454. ISSN 2190-4286. DOI: https://doi.org/10.3762/bjnano.13.37 |
EXPORT metadate: Google Scholar Crossref CERIF DataCite Dublin Core |
Beilstein Journal of Nanotechnology | |
Volumul 13 / 2022 / ISSN 2190-4286 | |
|
|
DOI: https://doi.org/10.3762/bjnano.13.37 | |
Pag. 444-454 | |
Descarcă PDF | |
Rezumat | |
The hardware implementation of signal microprocessors based on superconducting technologies seems relevant for a number of niche tasks where performance and energy efficiency are critically important. In this paper, we consider the basic elements for superconducting neural networks on radial basis functions. We examine the static and dynamic activation functions of the proposed neuron. Special attention is paid to tuning the activation functions to a Gaussian form with relatively large amplitude. For the practical implementation of the required tunability, we proposed and investigated heterostructures designed for the implementation of adjustable inductors that consist of superconducting, ferromagnetic, and normal layers. |
|
Cuvinte-cheie networks on radial basis functions, Josephson circuits, radial basis functions (RBFs), spintronics, superconducting electronics, Superconducting neural network |
|
|
DataCite XML Export
<?xml version='1.0' encoding='utf-8'?> <resource xmlns:xsi='http://www.w3.org/2001/XMLSchema-instance' xmlns='http://datacite.org/schema/kernel-3' xsi:schemaLocation='http://datacite.org/schema/kernel-3 http://schema.datacite.org/meta/kernel-3/metadata.xsd'> <identifier identifierType='DOI'>10.3762/bjnano.13.37</identifier> <creators> <creator> <creatorName>Schegolev, A.E.</creatorName> <affiliation>Нии Ядерной Физики Имени Д. В. Скобельцына, МГУ, Rusia</affiliation> </creator> <creator> <creatorName>Klenov, N.</creatorName> <affiliation>Universitatea de Stat M.V. Lomonosov din Moscova, Rusia</affiliation> </creator> <creator> <creatorName>Bakurskiy, S.</creatorName> <affiliation>Нии Ядерной Физики Имени Д. В. Скобельцына, МГУ, Rusia</affiliation> </creator> <creator> <creatorName>Soloviev, I.</creatorName> <affiliation>Нии Ядерной Физики Имени Д. В. Скобельцына, МГУ, Rusia</affiliation> </creator> <creator> <creatorName>Kupriyanov, M.I.</creatorName> <affiliation>Нии Ядерной Физики Имени Д. В. Скобельцына, МГУ, Rusia</affiliation> </creator> <creator> <creatorName>Tereshonok , M.V.</creatorName> <affiliation>Universitatea Tehnică de Comunicații și Informatică din Moscova, Rusia</affiliation> </creator> <creator> <creatorName>Sidorenko, A.S.</creatorName> <affiliation>Institutul de Inginerie Electronică şi Nanotehnologii "D. Ghiţu", Moldova, Republica</affiliation> </creator> </creators> <titles> <title xml:lang='en'>Tunable superconducting neurons for networks based on radial basis functions</title> </titles> <publisher>Instrumentul Bibliometric National</publisher> <publicationYear>2022</publicationYear> <relatedIdentifier relatedIdentifierType='ISSN' relationType='IsPartOf'>2190-4286</relatedIdentifier> <subjects> <subject>networks on radial basis functions</subject> <subject>Josephson circuits</subject> <subject>radial basis functions (RBFs)</subject> <subject>spintronics</subject> <subject>superconducting electronics</subject> <subject>Superconducting neural network</subject> </subjects> <dates> <date dateType='Issued'>2022-07-01</date> </dates> <resourceType resourceTypeGeneral='Text'>Journal article</resourceType> <descriptions> <description xml:lang='en' descriptionType='Abstract'><p>The hardware implementation of signal microprocessors based on superconducting technologies seems relevant for a number of niche tasks where performance and energy efficiency are critically important. In this paper, we consider the basic elements for superconducting neural networks on radial basis functions. We examine the static and dynamic activation functions of the proposed neuron. Special attention is paid to tuning the activation functions to a Gaussian form with relatively large amplitude. For the practical implementation of the required tunability, we proposed and investigated heterostructures designed for the implementation of adjustable inductors that consist of superconducting, ferromagnetic, and normal layers.</p></description> </descriptions> <formats> <format>application/pdf</format> </formats> </resource>